[SPARK-12692][BUILD][MLLIB] Scala style: Fix the style violation (Spa…

…ce before "," or ":")

Fix the style violation (space before , and :).
This PR is a followup for apache#10643.

Author: Kousuke Saruta <[email protected]>

Closes apache#10684 from sarutak/SPARK-12692-followup-mllib.

examples/src/main/scala/org/apache/spark/examples/mllib/IsotonicRegressionExample.scala

@@ -25,7 +25,7 @@ import org.apache.spark.mllib.regression.{IsotonicRegression, IsotonicRegression
 
 object IsotonicRegressionExample {
 
-  def main(args: Array[String]) : Unit = {
+  def main(args: Array[String]): Unit = {
 
     val conf = new SparkConf().setAppName("IsotonicRegressionExample")
     val sc = new SparkContext(conf)

examples/src/main/scala/org/apache/spark/examples/mllib/NaiveBayesExample.scala

@@ -27,7 +27,7 @@ import org.apache.spark.mllib.regression.LabeledPoint
 
 object NaiveBayesExample {
 
-  def main(args: Array[String]) : Unit = {
+  def main(args: Array[String]): Unit = {
     val conf = new SparkConf().setAppName("NaiveBayesExample")
     val sc = new SparkContext(conf)
     // $example on$

examples/src/main/scala/org/apache/spark/examples/mllib/RegressionMetricsExample.scala

@@ -27,7 +27,7 @@ import org.apache.spark.mllib.util.MLUtils
 import org.apache.spark.sql.SQLContext
 
 object RegressionMetricsExample {
-  def main(args: Array[String]) : Unit = {
+  def main(args: Array[String]): Unit = {
     val conf = new SparkConf().setAppName("RegressionMetricsExample")
     val sc = new SparkContext(conf)
     val sqlContext = new SQLContext(sc)

mllib/src/main/scala/org/apache/spark/ml/classification/OneVsRest.scala

@@ -113,13 +113,13 @@ final class OneVsRestModel private[ml] (
         val updateUDF = udf { (predictions: Map[Int, Double], prediction: Vector) =>
           predictions + ((index, prediction(1)))
         }
-        val transformedDataset = model.transform(df).select(columns : _*)
+        val transformedDataset = model.transform(df).select(columns: _*)
         val updatedDataset = transformedDataset
           .withColumn(tmpColName, updateUDF(col(accColName), col(rawPredictionCol)))
         val newColumns = origCols ++ List(col(tmpColName))
 
         // switch out the intermediate column with the accumulator column
-        updatedDataset.select(newColumns : _*).withColumnRenamed(tmpColName, accColName)
+        updatedDataset.select(newColumns: _*).withColumnRenamed(tmpColName, accColName)
     }
 
     if (handlePersistence) {

mllib/src/main/scala/org/apache/spark/ml/feature/RFormula.scala

@@ -238,7 +238,7 @@ private class ColumnPruner(columnsToPrune: Set[String]) extends Transformer {
 
   override def transform(dataset: DataFrame): DataFrame = {
     val columnsToKeep = dataset.columns.filter(!columnsToPrune.contains(_))
-    dataset.select(columnsToKeep.map(dataset.col) : _*)
+    dataset.select(columnsToKeep.map(dataset.col): _*)
   }
 
   override def transformSchema(schema: StructType): StructType = {

mllib/src/main/scala/org/apache/spark/ml/feature/VectorAssembler.scala

@@ -102,7 +102,7 @@ class VectorAssembler(override val uid: String)
       }
     }
 
-    dataset.select(col("*"), assembleFunc(struct(args : _*)).as($(outputCol), metadata))
+    dataset.select(col("*"), assembleFunc(struct(args: _*)).as($(outputCol), metadata))
   }
 
   override def transformSchema(schema: StructType): StructType = {

mllib/src/main/scala/org/apache/spark/ml/tree/impl/RandomForest.scala

@@ -474,7 +474,7 @@ private[ml] object RandomForest extends Logging {
     val nodeToFeatures = getNodeToFeatures(treeToNodeToIndexInfo)
     val nodeToFeaturesBc = input.sparkContext.broadcast(nodeToFeatures)
 
-    val partitionAggregates : RDD[(Int, DTStatsAggregator)] = if (nodeIdCache.nonEmpty) {
+    val partitionAggregates: RDD[(Int, DTStatsAggregator)] = if (nodeIdCache.nonEmpty) {
       input.zip(nodeIdCache.get.nodeIdsForInstances).mapPartitions { points =>
         // Construct a nodeStatsAggregators array to hold node aggregate stats,
         // each node will have a nodeStatsAggregator
@@ -825,7 +825,7 @@ private[ml] object RandomForest extends Logging {
   protected[tree] def findSplits(
       input: RDD[LabeledPoint],
       metadata: DecisionTreeMetadata,
-      seed : Long): Array[Array[Split]] = {
+      seed: Long): Array[Array[Split]] = {
 
     logDebug("isMulticlass = " + metadata.isMulticlass)
 

mllib/src/main/scala/org/apache/spark/mllib/clustering/GaussianMixtureModel.scala

@@ -177,7 +177,7 @@ object GaussianMixtureModel extends Loader[GaussianMixtureModel] {
   }
 
   @Since("1.4.0")
-  override def load(sc: SparkContext, path: String) : GaussianMixtureModel = {
+  override def load(sc: SparkContext, path: String): GaussianMixtureModel = {
     val (loadedClassName, version, metadata) = Loader.loadMetadata(sc, path)
     implicit val formats = DefaultFormats
     val k = (metadata \ "k").extract[Int]

mllib/src/main/scala/org/apache/spark/mllib/fpm/FPGrowth.scala

@@ -134,7 +134,7 @@ object FPGrowthModel extends Loader[FPGrowthModel[_]] {
       loadImpl(freqItemsets, sample)
     }
 
-    def loadImpl[Item : ClassTag](freqItemsets: DataFrame, sample: Item): FPGrowthModel[Item] = {
+    def loadImpl[Item: ClassTag](freqItemsets: DataFrame, sample: Item): FPGrowthModel[Item] = {
       val freqItemsetsRDD = freqItemsets.select("items", "freq").map { x =>
         val items = x.getAs[Seq[Item]](0).toArray
         val freq = x.getLong(1)

mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala

@@ -279,7 +279,7 @@ class DenseMatrix @Since("1.3.0") (
   }
 
   override def hashCode: Int = {
-    com.google.common.base.Objects.hashCode(numRows : Integer, numCols: Integer, toArray)
+    com.google.common.base.Objects.hashCode(numRows: Integer, numCols: Integer, toArray)
   }
 
   private[mllib] def toBreeze: BM[Double] = {

mllib/src/main/scala/org/apache/spark/mllib/pmml/export/BinaryClassificationPMMLModelExport.scala

@@ -27,9 +27,9 @@ import org.apache.spark.mllib.regression.GeneralizedLinearModel
  * PMML Model Export for GeneralizedLinearModel class with binary ClassificationModel
  */
 private[mllib] class BinaryClassificationPMMLModelExport(
-    model : GeneralizedLinearModel,
-    description : String,
-    normalizationMethod : RegressionNormalizationMethodType,
+    model: GeneralizedLinearModel,
+    description: String,
+    normalizationMethod: RegressionNormalizationMethodType,
     threshold: Double)
   extends PMMLModelExport {
 

mllib/src/main/scala/org/apache/spark/mllib/pmml/export/KMeansPMMLModelExport.scala

@@ -26,14 +26,14 @@ import org.apache.spark.mllib.clustering.KMeansModel
 /**
  * PMML Model Export for KMeansModel class
  */
-private[mllib] class KMeansPMMLModelExport(model : KMeansModel) extends PMMLModelExport{
+private[mllib] class KMeansPMMLModelExport(model: KMeansModel) extends PMMLModelExport{
 
   populateKMeansPMML(model)
 
   /**
    * Export the input KMeansModel model to PMML format.
    */
-  private def populateKMeansPMML(model : KMeansModel): Unit = {
+  private def populateKMeansPMML(model: KMeansModel): Unit = {
     pmml.getHeader.setDescription("k-means clustering")
 
     if (model.clusterCenters.length > 0) {

mllib/src/main/scala/org/apache/spark/mllib/tree/DecisionTree.scala

@@ -600,7 +600,7 @@ object DecisionTree extends Serializable with Logging {
     val nodeToFeatures = getNodeToFeatures(treeToNodeToIndexInfo)
     val nodeToFeaturesBc = input.sparkContext.broadcast(nodeToFeatures)
 
-    val partitionAggregates : RDD[(Int, DTStatsAggregator)] = if (nodeIdCache.nonEmpty) {
+    val partitionAggregates: RDD[(Int, DTStatsAggregator)] = if (nodeIdCache.nonEmpty) {
       input.zip(nodeIdCache.get.nodeIdsForInstances).mapPartitions { points =>
         // Construct a nodeStatsAggregators array to hold node aggregate stats,
         // each node will have a nodeStatsAggregator

mllib/src/main/scala/org/apache/spark/mllib/tree/model/Node.scala

@@ -83,7 +83,7 @@ class Node @Since("1.2.0") (
    * @return predicted value
    */
   @Since("1.1.0")
-  def predict(features: Vector) : Double = {
+  def predict(features: Vector): Double = {
     if (isLeaf) {
       predict.predict
     } else {

mllib/src/main/scala/org/apache/spark/mllib/util/LinearDataGenerator.scala

@@ -175,7 +175,7 @@ object LinearDataGenerator {
       nfeatures: Int,
       eps: Double,
       nparts: Int = 2,
-      intercept: Double = 0.0) : RDD[LabeledPoint] = {
+      intercept: Double = 0.0): RDD[LabeledPoint] = {
     val random = new Random(42)
     // Random values distributed uniformly in [-0.5, 0.5]
     val w = Array.fill(nfeatures)(random.nextDouble() - 0.5)

mllib/src/test/scala/org/apache/spark/mllib/classification/SVMSuite.scala

@@ -45,7 +45,7 @@ object SVMSuite {
     nPoints: Int,
     seed: Int): Seq[LabeledPoint] = {
     val rnd = new Random(seed)
-    val weightsMat = new DoubleMatrix(1, weights.length, weights : _*)
+    val weightsMat = new DoubleMatrix(1, weights.length, weights: _*)
     val x = Array.fill[Array[Double]](nPoints)(
         Array.fill[Double](weights.length)(rnd.nextDouble() * 2.0 - 1.0))
     val y = x.map { xi =>

mllib/src/test/scala/org/apache/spark/mllib/stat/StreamingTestSuite.scala

@@ -27,7 +27,7 @@ import org.apache.spark.util.random.XORShiftRandom
 
 class StreamingTestSuite extends SparkFunSuite with TestSuiteBase {
 
-  override def maxWaitTimeMillis : Int = 30000
+  override def maxWaitTimeMillis: Int = 30000
 
   test("accuracy for null hypothesis using welch t-test") {
     // set parameters